justinzeus/scholarr
1
0
Fork 0
Code Issues 1 Pull requests 18 Projects Releases Packages Wiki Activity Actions

ci: add ruff linting and mypy type checking

Browse source 
Add ruff and mypy to dev dependencies with configuration in pyproject.toml.
Add a lint CI job that runs ruff check, ruff format --check, and mypy.
Auto-fix import sorting and formatting across the codebase. Exclude
alembic/versions from linting (auto-generated migrations). Ignore B008
(FastAPI Depends pattern) and RUF001 (unicode in user-facing strings).

21 ruff lint errors and 50 mypy errors remain for manual review.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Justin Visser 2026-02-26 22:11:41 +01:00
parent 399276ea69
commit bf04c77aa9
137 changed files with 3066 additions and 1900 deletions
Download patch file Download diff file Expand all files Collapse all files

27
app/services/domains/openalex/matching.py
View file

@ -24,11 +24,11 @@ def _clean_string(s: str | None) -> str:
def _author_overlap_score(target_authors: str | None, candidate_authors: list[str]) -> bool:
if not target_authors or not candidate_authors:
return False
target_clean = _clean_string(target_authors)
if not target_clean:
return False
for candidate in candidate_authors:
cand_clean = _clean_string(candidate)
if cand_clean and (cand_clean in target_clean or target_clean in cand_clean):
@ -36,7 +36,7 @@ def _author_overlap_score(target_authors: str | None, candidate_authors: list[st
# Alternatively check rapidfuzz token_set_ratio
if cand_clean and fuzz.token_set_ratio(target_clean, cand_clean) > 80:
return True
return False
@ -62,12 +62,12 @@ def find_best_match(
for cand in candidates:
if not cand.title:
continue
clean_cand = _clean_string(cand.title)
# Primary sort: string similarity ratio
score = fuzz.ratio(clean_target, clean_cand)
if score >= TITLE_MATCH_THRESHOLD:
scored_candidates.append((score, cand))
@ -76,13 +76,12 @@ def find_best_match(
# Sort descending by score
scored_candidates.sort(key=lambda x: x[0], reverse=True)
best_score = scored_candidates[0][0]
# Extract all candidates within the tiebreaker margin
top_scored_candidates = [
(score, cand) for score, cand in scored_candidates
if best_score - score <= TIEBREAKER_MARGIN
(score, cand) for score, cand in scored_candidates if best_score - score <= TIEBREAKER_MARGIN
]
if len(top_scored_candidates) == 1:
@ -91,18 +90,18 @@ def find_best_match(
# We have a tie or near-tie. Use year and author overlap to break the tie.
# Score candidates: +1 for year match (within 1 year), +1 for author overlap
tiebreaker_scores: list[tuple[int, float, OpenAlexWork]] = []
for original_score, cand in top_scored_candidates:
tb_score = 0
if target_year is not None and cand.publication_year is not None:
if abs(target_year - cand.publication_year) <= 1:
tb_score += 1
candidate_author_names = [a.display_name for a in cand.authors if a.display_name]
if _author_overlap_score(target_authors, candidate_author_names):
tb_score += 1
tiebreaker_scores.append((tb_score, original_score, cand))
tiebreaker_scores.sort(key=lambda x: (x[0], x[1]), reverse=True)
return tiebreaker_scores[0][2]